List directory tree structure in python?

Question

I know that we can use os.walk() to list all sub-directories or all files in a directory. However, I would like to list the full directory tree content:

• Subdirectory 1:
  • file11
  • file12
  • Sub-sub-directory 11:
    • file111
    • file112
• Subdirectory 2:
  • file21
  • sub-sub-directory 21
  • sub-sub-directory 22
    
    • sub-sub-sub-directory 221
      • file 2211

How to best achieve this in Python?

Answer 1

Based on this fantastic post

http://code.activestate.com/recipes/217212-treepy-graphically-displays-the-directory-structur/

Here es a refinement to behave exactly like

http://linux.die.net/man/1/tree

#!/usr/bin/env python2
# -*- coding: utf-8 -*-

# tree.py
#
# Written by Doug Dahms
#
# Prints the tree structure for the path specified on the command line

from os import listdir, sep
from os.path import abspath, basename, isdir
from sys import argv

def tree(dir, padding, print_files=False, isLast=False, isFirst=False):
    if isFirst:
        print padding.decode('utf8')[:-1].encode('utf8') + dir
    else:
        if isLast:
            print padding.decode('utf8')[:-1].encode('utf8') + '└── ' + basename(abspath(dir))
        else:
            print padding.decode('utf8')[:-1].encode('utf8') + '├── ' + basename(abspath(dir))
    files = []
    if print_files:
        files = listdir(dir)
    else:
        files = [x for x in listdir(dir) if isdir(dir + sep + x)]
    if not isFirst:
        padding = padding + '   '
    files = sorted(files, key=lambda s: s.lower())
    count = 0
    last = len(files) - 1
    for i, file in enumerate(files):
        count += 1
        path = dir + sep + file
        isLast = i == last
        if isdir(path):
            if count == len(files):
                if isFirst:
                    tree(path, padding, print_files, isLast, False)
                else:
                    tree(path, padding + ' ', print_files, isLast, False)
            else:
                tree(path, padding + '│', print_files, isLast, False)
        else:
            if isLast:
                print padding + '└── ' + file
            else:
                print padding + '├── ' + file

def usage():
    return '''Usage: %s [-f] 
Print tree structure of path specified.
Options:
-f      Print files as well as directories
PATH    Path to process''' % basename(argv[0])

def main():
    if len(argv) == 1:
        print usage()
    elif len(argv) == 2:
        # print just directories
        path = argv[1]
        if isdir(path):
            tree(path, '', False, False, True)
        else:
            print 'ERROR: \'' + path + '\' is not a directory'
    elif len(argv) == 3 and argv[1] == '-f':
        # print directories and files
        path = argv[2]
        if isdir(path):
            tree(path, '', True, False, True)
        else:
            print 'ERROR: \'' + path + '\' is not a directory'
    else:
        print usage()

if __name__ == '__main__':
    main()

Answer 2

You can execute 'tree' command of Linux shell.

Installation:

   ~$sudo apt install tree

Using in python

    >>> import os
    >>> os.system('tree <desired path>')

Example:

    >>> os.system('tree ~/Desktop/myproject')

This gives you a cleaner structure and is visually more comprehensive and easy to type.

Answer 3

Maybe faster than @ellockie ( Maybe )

import os
def file_writer(text):
    with open("folder_structure.txt","a") as f_output:
        f_output.write(text)
def list_files(startpath):


    for root, dirs, files in os.walk(startpath):
        level = root.replace(startpath, '').count(os.sep)
        indent = '\t' * 1 * (level)
        output_string = '{}{}/ \n'.format(indent, os.path.basename(root))
        file_writer(output_string)
        subindent = '\t' * 1 * (level + 1)
        output_string = '%s %s \n' %(subindent,[f for f in files])
        file_writer(''.join(output_string))


list_files("/")

Test results in screenshot below:

Answer 4

Here's a function to do that with formatting:

import os

def list_files(startpath):
    for root, dirs, files in os.walk(startpath):
        level = root.replace(startpath, '').count(os.sep)
        indent = ' ' * 4 * (level)
        print('{}{}/'.format(indent, os.path.basename(root)))
        subindent = ' ' * 4 * (level + 1)
        for f in files:
            print('{}{}'.format(subindent, f))

Answer 5

A solution without your indentation:

for path, dirs, files in os.walk(path):
  print path
  for f in files:
    print f

os.walk already does the top-down, depth-first walk you are looking for.

Ignoring the dirs list prevents the overlapping you mention.

Answer 6

Similar to answers above, but for python3, arguably readable and arguably extensible:

from pathlib import Path

class DisplayablePath(object):
    display_filename_prefix_middle = '├──'
    display_filename_prefix_last = '└──'
    display_parent_prefix_middle = '    '
    display_parent_prefix_last = '│   '

    def __init__(self, path, parent_path, is_last):
        self.path = Path(str(path))
        self.parent = parent_path
        self.is_last = is_last
        if self.parent:
            self.depth = self.parent.depth + 1
        else:
            self.depth = 0

    @property
    def displayname(self):
        if self.path.is_dir():
            return self.path.name + '/'
        return self.path.name

    @classmethod
    def make_tree(cls, root, parent=None, is_last=False, criteria=None):
        root = Path(str(root))
        criteria = criteria or cls._default_criteria

        displayable_root = cls(root, parent, is_last)
        yield displayable_root

        children = sorted(list(path
                               for path in root.iterdir()
                               if criteria(path)),
                          key=lambda s: str(s).lower())
        count = 1
        for path in children:
            is_last = count == len(children)
            if path.is_dir():
                yield from cls.make_tree(path,
                                         parent=displayable_root,
                                         is_last=is_last,
                                         criteria=criteria)
            else:
                yield cls(path, displayable_root, is_last)
            count += 1

    @classmethod
    def _default_criteria(cls, path):
        return True

    @property
    def displayname(self):
        if self.path.is_dir():
            return self.path.name + '/'
        return self.path.name

    def displayable(self):
        if self.parent is None:
            return self.displayname

        _filename_prefix = (self.display_filename_prefix_last
                            if self.is_last
                            else self.display_filename_prefix_middle)

        parts = ['{!s} {!s}'.format(_filename_prefix,
                                    self.displayname)]

        parent = self.parent
        while parent and parent.parent is not None:
            parts.append(self.display_parent_prefix_middle
                         if parent.is_last
                         else self.display_parent_prefix_last)
            parent = parent.parent

        return ''.join(reversed(parts))

Example usage:

paths = DisplayablePath.make_tree(Path('doc'))
for path in paths:
    print(path.displayable())

Example output:

doc/
├── _static/
│   ├── embedded/
│   │   ├── deep_file
│   │   └── very/
│   │       └── deep/
│   │           └── folder/
│   │               └── very_deep_file
│   └── less_deep_file
├── about.rst
├── conf.py
└── index.rst

Notes

• This uses recursion. It will raise a RecursionError on really deep folder trees
• The tree is lazily evaluated. It should behave well on really wide folder trees. Immediate children of a given folder are not lazily evaluated, though.

Edit:

• Added bonus! criteria callback for filtering paths.